management-talk

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow reads JIRA tickets via API GET /rest/api/3/issue/<KEY>?fields=summary,status,priority,assignee,comment, ingesting outsider-authored comments and descriptions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching data via a JIRA REST API endpoint (GET /rest/api/3/issue/...), which represents a runtime operational API dependency with no specified base URL, provenance, or authenticated host.